{"id":"W4410964123","doi":"10.26434/chemrxiv-2025-h69wz","title":"A Data-Driven Workflow for Nanomedicine Optimization Using Active Learning and Automated Experimentation","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"3D Printing in Biomedical Research","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Canada First Research Excellence Fund; University of Toronto","keywords":"Workflow; Nanomedicine; Computer science; Active learning (machine learning); Artificial intelligence; Engineering; Database; Nanoparticle; Chemical engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003764679,0.001979572,0.00116306,0.0009698814,0.0006184172,0.00213587,0.002177739,0.001335725,0.004934203],"category_scores_gemma":[0.006337826,0.0008508445,0.001690712,0.0006788122,0.0009891773,0.001112154,0.001979922,0.002330803,0.00184735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001034456,"about_ca_system_score_gemma":0.002488922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002133688,"about_ca_topic_score_gemma":0.002976606,"domain_scores_codex":[0.998243,0.0005435935,0.0001565453,0.0005190274,0.0004280312,0.0001097225],"domain_scores_gemma":[0.9963972,0.00219907,0.0002272321,0.0005444952,0.0005045944,0.0001274188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006204987,0.0004838254,0.002371385,0.0007903312,0.0002033139,0.0003185747,0.0004230881,0.6701937,0.04381946,0.01598646,0.005414265,0.2593751],"study_design_scores_gemma":[0.00006702456,0.0001105583,0.0002377807,0.00002513102,0.00001661199,0.0000332575,0.00003191828,0.9632183,0.01765536,0.01379241,0.004782158,0.00002956812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006222984,0.0001002262,0.983184,0.0001433534,0.00002512426,0.0002464538,0.0002749721,0.00859228,0.001210565],"genre_scores_gemma":[0.1273475,0.0001486333,0.8682356,0.000158302,0.00002278981,0.001217983,0.001090233,0.0006808184,0.001098153],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004934203,"threshold_uncertainty_score":0.01990974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06226013160341773,"score_gpt":0.3806930317557101,"score_spread":0.3184329001522923,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}